Automated Measurement of Net Water Uptake From Baseline and Follow-Up CTs in Patients With Large Vessel Occlusion Stroke

Abstract

Quantifying the extent and evolution of cerebral edema developing after stroke is an important but challenging goal. Lesional net water uptake (NWU) is a promising CT-based biomarker of edema, but its measurement requires manually delineating infarcted tissue and mirrored regions in the contralateral hemisphere. We implement an imaging pipeline capable of automatically segmenting the infarct region and calculating NWU from both baseline and follow-up CTs of large-vessel occlusion (LVO) patients. Infarct core is extracted from CT perfusion images using a deconvolution algorithm while infarcts on follow-up CTs were segmented from non-contrast CT (NCCT) using a deep-learning algorithm. These infarct masks were flipped along the brain midline to generate mirrored regions in the contralateral hemisphere of NCCT; NWU was calculated as one minus the ratio of densities between regions, removing voxels segmented as CSF and with HU outside thresholds of 20-80 (normal hemisphere and baseline CT) and 0-40 (infarct region on follow-up). Automated results were compared with those obtained using manually-drawn infarcts and an ASPECTS region-of-interest based method that samples densities within the infarct and normal hemisphere, using intraclass correlation coefficient (ρ). This was tested on serial CTs from 55 patients with anterior circulation LVO (including 66 follow-up CTs). Baseline NWU using automated core was 4.3% (IQR 2.6-7.3) and correlated with manual measurement (ρ = 0.80, p < 0.0001) and ASPECTS (r = -0.60, p = 0.0001). Automatically segmented infarct volumes (median 110-ml) correlated to manually-drawn volumes (ρ = 0.96, p < 0.0001) with median Dice similarity coefficient of 0.83 (IQR 0.72-0.90). Automated NWU was 24.6% (IQR 20-27) and highly correlated to NWU from manually-drawn infarcts (ρ = 0.98) and the sampling-based method (ρ = 0.68, both p < 0.0001). We conclude that this automated imaging pipeline is able to accurately quantify region of infarction and NWU from serial CTs and could be leveraged to study the evolution and impact of edema in large cohorts of stroke patients.

Keywords: cerebral edema area; computed tomography; image segmentation; machine learning; stroke.

Figure 1

Outline of manual vs. automated techniques for estimation of net water uptake from baseline (top panels) and follow-up (bottom panel) CT scans of stroke patients. The RAPID core output (A) from CTP processing is used to determine the ASPECTS regions to be used for manual estimation of NWU from baseline NCCT (B). Regions-of-interest (ROIs) are placed in these regions within the affected hemisphere (orange) and matched ROIs are placed in the contralateral hemisphere (purple). Manual NWU is calculated as one minus the ratio of mean densities of the two sets of ROIs. For automated measurement of NWU on baseline CTs, CBF maps (C) are generated from raw CTP data (as fully detailed in the Supplementary Methods and shown in Supplementary Figure 1). The core mask (defined by thresholding at CBF < 30% of normal) is then registered and overlaid onto the NCCT (blue region in D). This infarct region is then flipped across the midline (purple region; method fully outlined in the Supplementary Methods and shown in Supplementary Figure 2) to create a matching mirror region (E). Automated NWU is calculated as one minus the mean densities of these two regions, after removing voxels of CSF (from separate CSF segmentation) or with HU density below 20 or above 80 from both regions (removed voxels shown in white). Lower panels show similar workflow for follow-up CTs (or baseline CTs with visible hypodensity). ROIs are placed within ASPECTS regions within the visible infarct and matching ROIs are placed in the contralateral hemisphere to calculate manual ROI-based NWU (F). The infarct region is also manually segmented (yellow, G). A deep learning-algorithm is applied to automatically segment regions of hypodensity and generate an infarct mask (blue, H). Infarct regions are then flipped to create matching mirror ROIs (purple, I). Regions of CSF are then removed, as are voxels outside the thresholds (HU 0–40 for infarct, 20–80 for normal brain). Automated NWU is then calculated. In this example, manual NWU on baseline CT was 16.0 and automated NWU was 12.3. For follow-up CT, the manual infarct volume was 135 ml and the automated volume was 143 ml. The manual NWU was 29.8 using ASPECTS ROI-method, 25.4 using the whole manual infarct, compared with 25.0 for the fully automated NWU.

Figure 2

Flow of stroke patients assessed for eligibility for this imaging analysis.

Figure 3

Comparing manual vs. fully automated measurements of NWU. Baseline CT: (A) intraclass correlation, ρ = 0.80; (B) Bland-Altman plot. Follow-up CT: (C) intraclass correlation, ρ = 0.68; (D) Bland-Altman plot with points colored by hemorrhage transformation (HT) type. The dashed line in the scatter plot represents the line of identify between measurements. The dashed lines in the Bland-Altman plots represent the limits of agreement. The solid line represents the mean difference in measurement (bias).

Figure 4

Example of follow-up CT in a patient who developed a focal parenchymal hematoma within the region of infarction. (A) Original non-contrast CT with regions-of-interest manually placed within the infarct (avoiding hemorrhage) and in contralateral matching regions (avoiding CSF); (B) Blue region indicates automated segmentation of infarct lesion; (C) Processing of follow-up CT to measure NWU using automated infarct mask, with removal of voxels representing CSF (white regions within purple normal mask) and voxels outside the range of 0-40 HU (removing most regions of hemorrhage). The manual NWU was 21.0 and the fully automated NWU was 21.6.